A Novel Hybrid Model for Short-Term Forecasting in PV Power Generation

Abstract

The increasing use of solar power as a source of electricity has led to increased interest in forecasting its power output over short-time horizons. Short-term forecasts are needed for operational planning, switching sources, programming backup, reserve usage, and peak load matching. However, the output of a photovoltaic (PV) system is influenced by irradiation, cloud cover, and other weather conditions. These factors make it difficult to conduct short-term PV output forecasting. In this paper, an experimental database of solar power output, solar irradiance, air, and module temperature data has been utilized. It includes data from the Green Energy Office Building in Malaysia, the Taichung Thermal Plant of Taipower, and National Penghu University. Based on the historical PV power and weather data provided in the experiment, all factors that influence photovoltaic-generated energy are discussed. Moreover, five types of forecasting modules were developed and utilized to predict the one-hour-ahead PV output. They include the ARIMA, SVM, ANN, ANFIS, and the combination models using GA algorithm. Forecasting results show the high precision and efficiency of this combination model. Therefore, the proposed model is suitable for ensuring the stable operation of a photovoltaic generation system.

Application of DC-AC Hybrid Grid and Solar Photovoltaic Generation with Battery Storage Using Smart Grid

“…Therefore, efficient use of these resources is a key route to deal with the ever increasing crisis in energy sector. Environmental awareness from local and foreign platforms has made the clean power demand progressively significant [2]. Integration of renewable energy resources in existing system is going wild; therefore, proper results are not achieved yet due to the lack of professionals.…”

Machine Learning Based Photovoltaics (PV) Power Prediction Using Different Environmental Parameters of Qatar

“…A linear regression model and an ANN were applied to estimate daily global solar radiation [20,21]. Thirdly, a hybrid model can combine different models to overcome limitations characterizing one single technique [22]. In addition, "ensemble" methods [23] build predictive models by integrating multiple strategies in order to improve the overall prediction performance.…”

Real‐time monitoring and diagnosis of photovoltaic system degradation only using maximum power point—the Suns‐Vmp method

“…The understanding of degradation pathways, which is critical to establish the fundamental physics of PV degradation and promote reliability‐aware design, is still missing from these analyses. As a result, another online characterization approach—that can potentially identify degradation pathways from field data by machine learning algorithms—has gained attention: (d)Machine learning has been proved to be a potent tool to analyze massive data and generate useful insights for different applications. It can potentially provide valuable information on PV degradation by various statistical analyses (eg, regression, classification, clustering).…”